wanshuiyin/Auto-claude-code-research-in-sleep

16,964 stars · Last commit 2026-09-29

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

README preview

# Auto-claude-code-research-in-sleep (ARIS ⚔️🌙)

<p align="center">
  <a href="https://huggingface.co/papers/2605.03042">
    <img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360">
  </a>
</p>

[![Quick Start](https://img.shields.io/badge/🚀_Quick_Start-3_commands-2E7D32?style=flat)](#quick-start) · [![How to run](https://img.shields.io/badge/🎯_How_to_run-direction_·_paper+code_·_build-orange?style=flat)](#how-to-run) · [![Technical Report](https://img.shields.io/badge/Technical%20Report-arXiv%3A2605.03042-b31b1b?style=flat&logo=arxiv)](https://huggingface.co/papers/2605.03042) · [![ARIS Intro (HTML)](https://img.shields.io/badge/ARIS%20Intro-HTML%20%C2%B7%20by%20%2Frender--html-1a4a8c?style=flat&logo=html5&logoColor=white)](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [![ARIS Intro Slides — VALSE 2026](https://img.shields.io/badge/Slides%20%40%20VALSE%202026-PDF%20%C2%B7%20by%20%2Fpaper--talk-EC1C24?style=flat&logo=adobeacrobatreader&logoColor=white)](docs/aris_intro_slides.pdf) · [![AI Agents](https://img.shields.io/badge/AI%20Agents-AGENT__GUIDE.md-4B2E83?style=flat&logo=readthedocs&logoColor=white)](AGENT_GUIDE.md) · [![Featured on PaperWeekly](https://img.shields.io/badge/Featured%20on-PaperWeekly-red?style=flat)](https://mp.weixin.qq.com/s/tDniVryVGjDkkkWl-5sTkQ) · [![GitHub stars](https://img.shields.io/github/stars/wanshuiyin/Auto-claude-code-research-in-sleep?style=flat&logo=github&logoColor=white&color=gold&label=Stars)](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [💬 Join Community](#community) · [![Cite](https://img.shields.io/badge/📖_Cite_Us-BibTeX-green?style=flat)](#citation)

🌱 *ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.*

💡 *Use ARIS as a skill-based workflow in [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_EN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md) / [DeepSeek Harness](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/dsh-aris#readme) — enjoy any way you like!*<br>*The executor drives, an independent model (Codex MCP by default) reviews. [Alternative model combinations](#alternative-model-combinations), including [ModelScope](docs/MODELSCOPE_GUIDE.md)-hosted models, need no Claude or OpenAI API.*

📦 *Those are the skills installed directly. Want it in one command? ARIS also ships as a standalone CLI and as plugins:* [![ARIS-Code CLI downloads](https://img.shields.io/github/downloads/wanshuiyin/Auto-claude-code-research-in-sleep/total?style=flat&logo=rust&logoColor=white&label=ARIS-Code%20standalone%20CLI&color=2E7D32)](docs/ARIS-Code-README_EN.md) · [![Claude Code plugin](https://img.shields.io/badge/Claude_Code-plugin-D97757?style=flat&logo=anthropic&logoColor=white)](#plugins) · [![Codex CLI plugin](https://img.shields.io/badge/Codex_CLI-plugin-000000?style=flat&logo=openai&logoColor=white)](#plugins) · [![DeepSeek Harness plugin](https://img.shields.io/badge/DeepSeek_Harness-dsh--aris-4D6BFE?style=flat)](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/dsh-aris#readme)

❗ ![IMPORTANT](https://img.shields.io/badge/IMPORTANT-red?style=flat-square) **codex-cli 0.154.0 removed `codex mcp-server` — the entry point every ARIS reviewer call used. No impact on ARIS:** the `codex` MCP server is now ARIS's own bridge over `codex exec` (`mcp-servers/codex-exec/`), same tools, same results, all 82 skills unchanged, `ultra` and per-thread resume intact. One re-registration is all it takes — **[already installed? → Quick Start step 2b](#quick-start)** · **[new install → step 2](#quick-start)** · [what changed](#whats-new).

**🧩 The ARIS family** — same method, other jobs. One line each; the details live in their own repos.

View full repository on GitHub →